Thoughtland: Natural Language Descriptions for Machine Learning n-dimensional Error Functions
نویسنده
چکیده
This demo showcases Thoughtland, an end-to-end system that takes training data and a selected machine learning model, produces a cloud of points via crossvalidation to approximate its error function, then uses model-based clustering to identify interesting components of the error function and natural language generation to produce an English text summarizing the error function.
منابع مشابه
On the Feasibility of Automatically Describing n-dimensional Objects
This paper introduces the problem of generating descriptions of n-dimensional spatial data by decomposing it via modelbased clustering. I apply the approach to the error function of supervised classification algorithms, a practical problem that uses Natural Language Generation for understanding the behaviour of a trained classifier. I demonstrate my system on a dataset taken from CoNLL shared t...
متن کاملTemporal Ordering of Event Descriptions
This paper describes a machine learning approach to ordering real world events based on their newswire descriptions. Understanding and ordering free form text has been a challenge in natural language processing (NLP) for many years, but only recently have machine learning techniques been utilized. We describe steps taken to advance the state of the art, focusing on learning temporal relations b...
متن کاملComputer-Aided TRIZ Ideality and Level of Invention Estimation Using Natural Language Processing and Machine Learning
Patent textual descriptions provide a wealth of information that can be used to understand the underlying design approaches that result in the generation of novel and innovative technology. This article will discuss a new approach for estimating Degree of Ideality and Level of Invention metrics from the theory of inventive problem solving (TRIZ) using patent textual information. Patent text inc...
متن کاملMachine Learning of Natural Language
In this article we provide an overview of recent research on the application of symbolic Machine Learning techniques to language data (Machine Learning of Natural Language, MLNL). Both in Quantitative Linguistics (QL) and in MLNL, the main goal is to describe the language as it is observed with rules, language models, or other descriptions. But whereas the motivation in QL is purely scientific ...
متن کاملLearning to Order Facts for Discourse Planning in Natural Language Generation
This paper presents a machine learning approach to discourse planning in natural language generation. More specifically, we address the problem of learning the most natural ordering of facts in discourse plans for a specific domain. We discuss our methodology and how it was instantiated using two different machine learning algorithms. A quantitative evaluation performed in the domain of museum ...
متن کامل